Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code class declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rant
    0.97
     buona
    0.78
     delic
    0.78
     koment
    0.78
     jeans
    0.78
     ge
    0.78
     dug
    0.78
     libertarian
    0.77
     eureka
    0.77
     peanuts
    0.77
    POSITIVE LOGITS
    Histogram
    0.71
     Histogram
    0.68
     Polynomial
    0.65
    Recursive
    0.64
    Legacy
    0.64
     Reactor
    0.63
    Floating
    0.63
    Ổ
    0.62
    Execution
    0.62
     Textile
    0.62
    Act Density 0.461%

    No Known Activations